Subpixel Change Detection Based on Radial Basis Function with Abundance Image Difference Measure for Remote Sensing Images

Recently, land cover change detection has become a research focus of remote sensing. To obtain the information from sensing images at fine spatial and temporal resolutions, subpixel is widely studied applied. In this paper, new method based on radial basis function (RBF) for proposed, in which abundance image difference measure (AIDM) designed utilized to enhance mapping (SPM) by borrowing distribution resolution decrease influence spectral unmixing error. First, coarse are used develop detection. Second, linear mixing modeling degradation procedure conducted produce two images, respectively. Then, AIDM RBF-based SPM comparing images. At last, proposed RBF-AIDM applied The synthetic Landsat-7 Enhanced Thematic Mapper Plus (ETM+) real case Landsat-8 Operational Land Imager (OLI) one Moderate Resolution Imaging Spectroradiometer (MODIS) undertaken validate method. experimental results indicate that can sufficiently error improve results.